Video recording method and system based on intelligent door lock

Abstract

One or more embodiments of the invention provide a video recording method and system based on an intelligent door lock, the method is applied to the intelligent door lock, and the method comprises the following steps: the intelligent door lock obtains a corresponding relation between face information and a first video shot by the intelligent door lock and from the time when the intelligent door lock detects the face information to the time when the intelligent door lock is unlocked; sending to the video equipment for storage; a neighbor intelligent door lock corresponding to the intelligent door lock sends a corresponding relation between the face information and a second video shot by the neighbor intelligent door lock from receiving a first message sent by the intelligent door lock to receiving a second message sent by the intelligent door lock to video equipment for storage; and a camera device deployed in a room corresponding to the intelligent door lock sends a corresponding relation between the face information and a third video shot by the camera device from the time when the camera device detects the face information to the time when the camera device does not detect the face information to a video recording device for storage. According to the invention, the whole-course video recording of the visitor visiting process can be realized.

Description

Technical Field

[0001] One or more embodiments of the present application relate to the technical field of smart home, and particularly to a video recording method and system based on a smart door lock. Background Art

[0002] The Internet of Things refers to a network that connects various information sensing devices (such as radio frequency identification, infrared sensors, laser scanners, global positioning systems, etc.) to objects (such as home appliances, household appliances, cars, buildings, etc.) through the Internet for communication and information exchange to achieve intelligent identification, positioning, tracking, monitoring, and management. It expands the concept of the Internet, no longer limited to information exchange between people, but also enabling information interaction between things and between things and people. Internet of Things devices refer to those physical objects that can be connected through the Internet and exchange data with other devices or systems. These devices are usually embedded with sensors, software, and other technologies to achieve data collection, data interaction with the Internet or other devices, and automation functions. Common types of Internet of Things devices include smart home devices (such as smart door locks, smart cameras, etc.), smart home appliances (such as smart refrigerators, smart air conditioners, etc.), wearable devices (such as smart watches, fitness trackers, etc.), vehicle networking devices (such as in-vehicle units, smart traffic lights, etc.), healthcare Internet of Things devices (such as remote patient monitoring devices, drug management devices, etc.), etc.

[0003] The Internet of Things has become a bridge connecting the physical world and the digital world, greatly promoting the intelligent process of all walks of life. With the rapid development of Internet of Things technology and the in-depth promotion of smart city construction, the application of smart home devices in communities is becoming increasingly popular. Currently, many families have deployed smart door locks equipped with cameras and displays at their entrance doors. These smart door locks usually have functions such as face recognition, automatic and remote unlocking, and video intercom for visitors, providing users with convenient access management and security protection.

[0004] In practical applications, when someone visits, it is usually desired to record the visit process of the visitor so that the subsequent householders can review the visit process of the visitor through the corresponding video. Therefore, how to achieve convenient and reliable video recording of the visitor's visit process based on a smart door lock has become a highly concerned issue. Summary of the Invention

[0005] One or more embodiments of the present application provide the following technical solutions: The present application provides a video recording method based on a smart door lock, which is applied to a smart door lock; the method includes: Invoking the mounted camera to perform video shooting, and performing face detection on the captured video frames; When detecting face information from the video frame, send a first message containing the face information to a neighboring smart lock corresponding to the smart lock, so that the neighboring smart lock calls the equipped camera to take a video in response to the received first message; When detecting that the smart lock has been unlocked, obtain a first video captured by the smart lock, and send the correspondence between the face information and the first video to a video recording device deployed in the room corresponding to the smart lock for storage; and, send a second message to the neighboring smart lock, so that the neighboring smart lock obtains a second video captured by the neighboring smart lock in response to the received first message, and sends the correspondence between the face information and the second video to the video recording device for storage; and, send a third message containing the face information to a camera device deployed in the room, so that the camera device performs face detection on the captured video frame, and based on the face detection result, obtains a third video captured by the camera device, and sends the correspondence between the face information and the third video to the video recording device for storage; Wherein, the starting moment of shooting the first video is the moment when the smart lock detects the face information from the video frame, and the ending moment of shooting the first video is the moment when the smart lock detects that the smart lock has been unlocked; the starting moment of shooting the second video is the moment when the neighboring smart lock receives the first message, and the ending moment of shooting the second video is the moment when the neighboring smart lock receives the second message; the starting moment of shooting the third video is the moment when the camera device detects the face information from the video frame, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frame.

[0006] This application also provides a video recording system based on a smart lock, and the system includes a smart lock, a neighboring smart lock corresponding to the smart lock, a camera device and a video recording device deployed in the room corresponding to the smart lock; wherein: The smart lock calls the equipped camera to take a video and performs face detection on the captured video frame; When the smart lock detects the face information from the video frame, send a first message containing the face information to a neighboring smart lock corresponding to the smart lock; The neighboring smart lock calls the equipped camera to take a video in response to the received first message; When the intelligent door lock detects that the intelligent door lock has been unlocked, it acquires a first video captured by the intelligent door lock and sends the correspondence between the face information and the first video to a video recording device deployed in the room corresponding to the intelligent door lock for storage; and, sends a second message to the neighboring intelligent door lock; and, sends a third message containing the face information to a camera device deployed in the room; In response to the received first message, the neighboring intelligent door lock acquires a second video captured by the neighboring intelligent door lock and sends the correspondence between the face information and the second video to the video recording device for storage; In response to the received third message, the camera device performs face detection on the captured video frames, and based on the face detection result, acquires a third video captured by the camera device and sends the correspondence between the face information and the third video to the video recording device for storage; Wherein, the starting moment of shooting the first video is the moment when the intelligent door lock detects the face information from the video frames, and the ending moment of shooting the first video is the moment when the intelligent door lock detects that the intelligent door lock has been unlocked; the starting moment of shooting the second video is the moment when the neighboring intelligent door lock receives the first message, and the ending moment of shooting the second video is the moment when the neighboring intelligent door lock receives the second message; the starting moment of shooting the third video is the moment when the camera device detects the face information from the video frames, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames captured by itself.

[0007] In the above technical solution, the intelligent door lock can call the equipped camera to perform video shooting and perform face detection on the captured video frames, so as to acquire a first video captured by the intelligent door lock based on the face detection result. The starting moment of shooting the first video is the moment when the intelligent door lock detects the face information from the video frames captured by itself, and the ending moment of shooting the first video is the moment when the intelligent door lock detects that it has been unlocked. Furthermore, the correspondence between the face information and the first video can be sent to a video recording device deployed in the room corresponding to the intelligent door lock for storage. When the intelligent door lock detects that it has been unlocked, it can also send a third message to a camera device deployed in the room, so that in response to the received third message, the camera device performs face detection on the captured video frames and acquires a third video captured by the camera device based on the face detection result. The starting moment of shooting the third video is the moment when the camera device receives the third message, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames captured by itself. Furthermore, the correspondence between the face information and the third video can be sent to the video recording device for storage.

[0008] By adopting the above method, through the linkage between the intelligent door lock, the camera device and the video recording device deployed in the room corresponding to the intelligent door lock, the whole process video recording of the visitor's visit process can be realized. Description of the Drawings

[0009] The drawings required for the description of the exemplary embodiments will be described below, where: Figure 1 is a schematic diagram of an intelligent door lock management system shown in an exemplary embodiment of the present application.

[0010] Figure 2 is a flowchart of a video recording method based on an intelligent door lock shown in an exemplary embodiment of the present application.

[0011] Figure 3 is a schematic diagram of another intelligent door lock management system shown in an exemplary embodiment of the present application.

[0012] Figure 4 is a flowchart of another video recording method based on an intelligent door lock shown in an exemplary embodiment of the present application.

[0013] Figure 5 is a schematic diagram of the structure of a device shown in an exemplary embodiment of the present application.

[0014] Figure 6 is a block diagram of a video recording device based on an intelligent door lock shown in an exemplary embodiment of the present application. Detailed Embodiments

[0015] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with one or more embodiments of the present application. On the contrary, they are only examples consistent with some aspects of one or more embodiments of the present application.

[0016] It should be noted that in other embodiments, the steps of the corresponding methods are not necessarily executed in the order shown and described in the present application. In some other embodiments, the steps included in the method may be more or less than those described in the present application. In addition, a single step described in the present application may be decomposed into multiple steps for description in other embodiments; and multiple steps described in the present application may also be combined into a single step for description in other embodiments.

[0017] For an intelligent door lock, it usually has functions such as face recognition, automatic and remote unlocking, and video intercom for visitors, providing users with convenient access management and security protection.

[0018] In practical applications, when someone visits, it is usually desired to record the entire visiting process of the visitor so that the subsequent householders can review the entire visiting process through the corresponding video recording. Therefore, how to achieve convenient and reliable video recording of the visiting process based on an intelligent door lock has become a much - concerned issue.

[0019] This application provides a technical solution for video recording based on an intelligent door lock. In this technical solution, the intelligent door lock can call the equipped camera to take a video, and perform face detection on the captured video frames. Based on the face detection results, a first video captured by the intelligent door lock is obtained. The starting moment of shooting the first video is the moment when the intelligent door lock detects face information from the video frames captured by itself, and the ending moment of shooting the first video is the moment when the intelligent door lock detects that it has been unlocked. Then, the corresponding relationship between the face information and the first video can be sent to a video recording device deployed in the room corresponding to the intelligent door lock for storage. When the intelligent door lock detects that it has been unlocked, it can also send a third message to the camera device deployed in this room, so that in response to the received third message, the camera device performs face detection on the captured video frames, and based on the face detection results, a third video captured by the camera device is obtained. The starting moment of shooting the third video is the moment when the camera device receives the third message, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames captured by itself. Then, the corresponding relationship between the face information and the third video can be sent to the video recording device for storage.

[0020] By adopting the above - mentioned method, it is possible to achieve full - process video recording of the visitor's visiting process through the linkage among the intelligent door lock, the camera device deployed in the room corresponding to the intelligent door lock, and the video recording device.

[0021] Reference Figure 1 , Figure 1 is a schematic diagram of an intelligent door lock management system shown in an exemplary embodiment of this application.

[0022] As Figure 1As shown, in the above intelligent door lock management system, it may include multiple intelligent door locks and a door lock management platform for uniformly managing these intelligent door locks. Each intelligent door lock within a specific area (e.g., a community, a building, or a unit within a building) can access the Internet through Wi-Fi, cellular networks, or other wireless network communication technologies. At the same time, the door lock management platform within this area can also access the Internet through wired network communication technologies or wireless network communication technologies, so that these intelligent door locks and the door lock management platform can be connected through the Internet for communication and information exchange.

[0023] Specifically, each intelligent door lock can register its device on the above-mentioned door lock management platform to upload its own device information (e.g., device communication address, device geographical location, device operating status, etc.) to the door lock management platform for maintenance. Moreover, each intelligent door lock can also periodically synchronize its current device information to the door lock management platform to update the device information of this intelligent door lock maintained by the door lock management platform.

[0024] Taking one of the intelligent door locks as an example, when this intelligent door lock is first started after deployment, it can send a registration message to the above-mentioned door lock management platform. This registration message can include the device unique identifier of this intelligent door lock (e.g., device unique number), communication address (e.g., IP address, port number, MAC address, etc.), geographical location, associated household information, etc. Among them, the geographical location can specifically be data encoded using the standard geographical coding format for information such as building number, floor number, room number, etc.; the associated household information can include the identity information of one or more users using this intelligent door lock (e.g., personal password, face information, fingerprint information, etc., where the face information or fingerprint information can be feature vectors extracted from face images or fingerprint images). After receiving this registration message, the door lock management platform can store the corresponding relationships among various information such as the device unique identifier, communication address, geographical location, and associated household information in this registration message. In addition, this intelligent door lock can periodically send an information update message to the door lock management platform. This information update message can include the updated communication address, updated associated household information, etc. After receiving this information update message, the door lock management platform can update the corresponding stored information according to the updated information in this information update message.

[0025] The device information of each intelligent door lock maintained by the above-mentioned door lock management platform can be as shown in Table 1 below: Table 1

[0026] In Figure 1In the intelligent door lock management system shown, it may further include multiple camera devices and multiple video recording devices. Among them, the camera devices are used to capture videos, and the video recording devices are used to store videos and can play the stored videos. The camera devices in this application can be camera devices deployed in the room corresponding to the intelligent door lock to capture the stage of the visitor in the room. And in order to facilitate the original occupant of the room to view the visiting video of the visitor, the video recording device can also be deployed in the room corresponding to the intelligent door lock. The camera devices and video recording devices in a specific area can also be connected to the Internet through wired network communication technology or wireless network communication technology, and thus be connected to the above-mentioned door lock management platform through the Internet for communication and information exchange.

[0027] Similarly to the above intelligent door lock, each camera device and each video recording device can also upload its own device information to the above-mentioned door lock management platform for maintenance.

[0028] The device information of each camera device and each video recording device maintained by the above-mentioned door lock management platform can be as shown in Table 2 below: Table 2

[0029] In this application, the building, floor, room, etc. can be referred to by information such as building number, floor number, room number, etc. (the information itself or the encoded data of the information).

[0030] In the above intelligent door lock management system, the intelligent door lock, camera device, and video recording device can all communicate and exchange information with the door lock management platform. In this case, the door lock management platform can integrate and analyze the information reported by the intelligent door lock, camera device, and video recording device, and generate corresponding control instructions to be sent to the intelligent door lock, camera device, and video recording device to control them and make them perform corresponding operations.

[0031] Therefore, through the above-mentioned door lock management platform, the above-mentioned intelligent door lock, the above-mentioned camera device, and the above-mentioned video recording device can be linked to jointly complete video capture and video playback during the visitor's visit process.

[0032] Based on Figure 1 and referring to Figure 2 , Figure 2 is a flowchart of a video recording method based on an intelligent door lock shown in an exemplary embodiment of this application.

[0033] As Figure 2 shown, the above-mentioned video recording method based on an intelligent door lock can be applied to the intelligent door lock as shown in Figure 1 . This method can specifically include the following steps: Step 201: Call the onboard camera to capture a video and perform face detection on the captured video frames.

[0034] In this embodiment, in order to record the video during the visit of a visitor, the intelligent door lock can first call the camera carried by itself to take a video, and perform face detection on the video frames (i.e., the images used to form the video) captured by itself to confirm whether there is a visitor. If face information is detected in a certain video frame captured by the intelligent door lock, it can be considered that a visitor has arrived since the capture moment of this video frame.

[0035] Step 202: When face information is detected in the video frame, send a first message containing the face information to the neighboring intelligent door lock corresponding to the intelligent door lock, so that the neighboring intelligent door lock calls the camera carried by itself to take a video in response to the received first message.

[0036] In this embodiment, in order to improve the diversity of the video recording during the visit of a visitor, when the above intelligent door lock detects the above face information in the video frames captured by itself (i.e., the starting moment of the shooting of the above first video), it can send a message (which can be called the first message) containing the above face information to the neighboring intelligent door lock corresponding to the intelligent door lock.

[0037] The above neighboring intelligent door lock can call the camera carried by itself to take a video in response to the received first message.

[0038] Step 203: When it is detected that the intelligent door lock has been unlocked, obtain the first video captured by the intelligent door lock, and send the correspondence between the face information and the first video to the video recording device deployed in the room corresponding to the intelligent door lock for storage; wherein, the starting moment of the shooting of the first video is the moment when the intelligent door lock detects the face information in the video frame, and the ending moment of the shooting of the first video is the moment when the intelligent door lock detects that the intelligent door lock has been unlocked.

[0039] In this embodiment, the video (which can be called the first video) captured by the intelligent door lock can be obtained based on the face detection result of the video frames captured by the above intelligent door lock.

[0040] Specifically, as described above, it is generally considered that a visitor arrives starting from the moment when face information is detected in a certain video frame captured by the above-mentioned intelligent door lock. Therefore, the intelligent door lock can use the moment when face information is detected in this video frame as the starting moment of shooting the above-mentioned first video, and start recording the captured video frames from this starting moment. Correspondingly, after the intelligent door lock is unlocked, the visitor usually enters the room corresponding to the intelligent door lock (for example: the room where the intelligent door lock is deployed on the entrance door), resulting in the intelligent door lock being unable to capture the visitor anymore. Therefore, the intelligent door lock can use the moment when it detects that it has been unlocked as the ending moment of shooting the first video, and stop recording the captured video frames at this ending moment. In this case, the video formed by the video frames captured by the intelligent door lock during the period from this starting moment to this ending moment is the first video. That is to say, the first video captured by the intelligent door lock can be the video captured by the intelligent door lock by invoking the camera it is equipped with during the process from the moment when the user corresponding to the face information enters the shooting range of the camera of the intelligent door lock to the moment when the intelligent door lock detects that it has been unlocked.

[0041] For example, assume that the moment when the above-mentioned intelligent door lock detects face information from the video frames it captures is 16:30 on February 20, 2025, and the moment when the intelligent door lock detects that it has been unlocked is 16:35 on February 20, 2025. Then the video captured by the intelligent door lock during the period from 16:30 on February 20, 2025 to 16:35 on February 20, 2025 is the above-mentioned first video.

[0042] When the above-mentioned intelligent door lock obtains the above-mentioned first video, it can determine that the face information detected by the intelligent door lock at the starting moment of shooting the first video corresponds to the first video. Therefore, the intelligent door lock can send the corresponding relationship between the face information and the first video to the video recording device deployed in the room corresponding to the intelligent door lock. Specifically, the intelligent door lock can bind the face information with the first video, and send the bound face information and the first video to the video recording device together. When the video recording device receives the corresponding relationship between the face information and the first video, it can store this corresponding relationship, that is, it can obtain the face information and the first video, and store the face information and the first video in a corresponding manner.

[0043] In some embodiments, when the above-mentioned intelligent door lock invokes the camera it is equipped with for video shooting, it can specifically invoke the camera it is equipped with for real-time video shooting.

[0044] Alternatively, to reduce the load of the above smart door lock and relieve its burden, when the smart door lock calls the camera it is equipped with to take a video, it can specifically call the camera it is equipped with to take a video when it detects that a user enters the detection range of the smart door lock. Herein, the detection range refers to the area or distance within which a device or system can effectively identify, analyze, and respond.

[0045] In some embodiments, the above smart door lock can call the camera it is equipped with to achieve structured light ranging. That is, the smart door lock can perform structured light ranging on the user to obtain the distance between the user and the smart door lock, and compare this distance with a preset threshold to detect whether the distance between the user and the smart door lock is greater than the threshold. If the distance between the user and the smart door lock is not greater than the threshold, it can be considered that the user has entered the detection range of the smart door lock.

[0046] Structured light ranging is a three-dimensional measurement technology. It projects a specific pattern of light (usually stripes or grids) onto the target object, and then uses a camera to capture the deformed image formed by these lights on the object surface, thereby calculating the three-dimensional shape and distance information of the object. During the process of structured light ranging, first, the structured light system emits a set of known pattern lights to the object to be measured, and this pattern is usually a set of parallel lines or a complex grid pattern; then, one or more cameras can capture the light pattern projected onto the object from different angles. Due to the undulation of the object surface, the original regular light pattern will be distorted; finally, by analyzing the difference between the deformed pattern and the original pattern, the three-dimensional contour of the object can be reconstructed, and the specific position and distance of the object relative to the camera can be calculated.

[0047] In some embodiments, the above smart door lock can detect whether a user has entered the detection range of the smart door lock through the sensor it is equipped with for detecting the movement of an object.

[0048] Specifically, the detection range of the above smart door lock can be the sensing range of the sensor it is equipped with for detecting the movement of an object. In this case, when the smart door lock detects through the sensor that a user enters the sensing range of the sensor, it can determine that the user has entered the detection range of the smart door lock.

[0049] In some embodiments, the above sensor for detecting the movement of an object can specifically be a Passive Infrared (PIR) sensor or a radar sensor, and their main functions are to detect the presence or movement of an object (usually a person or an animal) in a certain area.

[0050] Among them, the PIR sensor senses whether a warm object enters its sensing range by detecting changes in infrared radiation in the environment; when a warm object moves, it changes the infrared radiation distribution in this area, and the PIR sensor can capture this change. The sensing range of the PIR sensor refers to the maximum distance and angular range within which the sensor can detect changes in infrared radiation.

[0051] The radar sensor detects the presence and movement of an object by emitting microwaves and receiving the reflected signals; according to the Doppler effect, if the frequency of the reflected wave changes, it indicates that there is an object in motion. The sensing range of the radar sensor refers to the effective distance within which the sensor emits microwaves and receives the reflected signals.

[0052] In some embodiments, in order to reduce the power consumption of the above-mentioned smart door lock and extend the operating duration of the smart door lock with the same amount of power, the default state of the smart door lock can be the sleep state, that is, it is in the standby mode with low power consumption and low activity by default, temporarily stopping the operation of most functions, but retaining basic data and settings.

[0053] For example, when the above-mentioned smart door lock is in the sleep state, its network function can also stop running. When the smart door lock detects that a user enters the detection range of the smart door lock, the network module (such as: WiFi module) in the smart door lock can be awakened to realize the normal operation of the network function.

[0054] In the above situation, when the smart door lock detects that a user enters the detection range of the smart door lock, it can switch from the sleep state to the running state, that is, switch to the normal working mode, all functions can be used, and corresponding tasks can be executed, so that the smart door lock can call the camera carried by itself to take a video and perform face detection on the captured video frames.

[0055] After the unlocking operation is completed, the above-mentioned smart door lock can switch back from the running state to the sleep state.

[0056] Step 204: When it is detected that the smart door lock has been unlocked, send a second message to the neighbor smart door lock, so that in response to the received first message, the neighbor smart door lock acquires a second video captured by the neighbor smart door lock, and sends the correspondence between the face information and the second video to the video recording device for storage; wherein, the starting moment of shooting the second video is the moment when the neighbor smart door lock receives the first message, and the ending moment of shooting the second video is the moment when the neighbor smart door lock receives the second message.

[0057] In this embodiment, when the intelligent door lock detects that it has been unlocked, it can also send a message (which can be called the second message) to the neighboring intelligent door lock. The second message may include the above-mentioned face information or may not include such face information.

[0058] The neighboring intelligent door lock can, in response to receiving the second message, obtain a video (which can be called the second video) captured by the neighboring intelligent door lock.

[0059] Specifically, the neighboring intelligent door lock can use the moment when it receives the first message as the starting moment of shooting the second video, and start recording the captured video frames from this starting moment. Correspondingly, the neighboring intelligent door lock can use the moment when it receives the second message as the ending moment of shooting the second video, and stop recording the captured video frames at this ending moment. In this case, the video formed by the video frames captured by the neighboring intelligent door lock during the period from this starting moment to this ending moment is the second video. That is to say, the second video captured by the neighboring intelligent door lock can be the video captured by the neighboring intelligent door lock by invoking the built-in camera during the process from when the neighboring intelligent door lock receives the first message to when the neighboring intelligent door lock receives the second message.

[0060] For example, assume that the moment when the neighboring intelligent door lock receives the first message is 16:30 on February 20, 2025, and the moment when the neighboring intelligent door lock receives the second message is 16:35 on February 20, 2025. Then the video captured by the neighboring intelligent door lock during the period from 16:30 on February 20, 2025 to 16:35 on February 20, 2025 is the above-mentioned second video.

[0061] When the neighboring intelligent door lock obtains the second video, it can determine that the face information in the first message and / or the second message corresponds to the second video. Therefore, the neighboring intelligent door lock can send the corresponding relationship between the face information and the second video to the above-mentioned video recording device. Specifically, the neighboring intelligent door lock can bind the face information to the second video, and send the bound face information and the second video together to the video recording device. When the video recording device receives the corresponding relationship between the face information and the second video, it can store this corresponding relationship, that is, it can obtain the face information and the second video, and store the face information and the second video corresponding to each other.

[0062] It should be noted that the neighboring intelligent door lock can also send the second video to the intelligent door lock, and the intelligent door lock can send the first video and the second video together to the video recording device for storage.

[0063] In some embodiments, the above-mentioned door lock management platform can determine the neighboring smart door locks of each smart door lock according to the address positions of the smart door locks. For example, the neighboring smart door lock of the smart door lock in Room 501, Unit 2, Building 1 can be the smart door lock in Room 502, Unit 2, Building 1. Among them, the shooting ranges of the cameras mounted on a smart door lock and its neighboring smart door lock can be relative, that is, the room corresponding to the smart door lock and the room corresponding to the neighboring smart door lock can be opposite rooms. For a smart door lock, the door lock management platform can send the device information of the neighboring smart door lock of the smart door lock to the smart door lock for maintenance, so that the smart door lock can communicate and exchange information with its neighboring smart door lock according to the device information of its neighboring smart door lock.

[0064] Alternatively, in actual applications, the user can also directly pre-set the device information of the neighboring smart door lock of the above-mentioned smart door lock in the smart door lock for maintenance, so that the smart door lock can communicate and exchange information with its neighboring smart door lock according to the device information of its neighboring smart door lock.

[0065] Step 205: When it is detected that the smart door lock has been unlocked, send a third message containing the face information to the camera device deployed in the room, so that the camera device, in response to the received third message, performs face detection on the captured video frames, obtains a third video captured by the camera device based on the face detection result, and sends the correspondence between the face information and the third video to the video recording device for storage; wherein, the starting moment of shooting the third video is the moment when the camera device detects the face information from the video frames, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames.

[0066] In this embodiment, when the above-mentioned smart door lock detects that it has been unlocked, it can also send a message (which can be called the third message) containing the above-mentioned face information to the camera device deployed in the room corresponding to the smart door lock.

[0067] When the above-mentioned camera device receives the above-mentioned third message, it can respond. Specifically, it can perform face detection on the video frames captured by itself and obtain a video (which can be called the third video) captured by the camera device based on the face detection result.

[0068] Specifically, the above-mentioned imaging device may use the moment when the above-mentioned third message is received as the starting moment of shooting the above-mentioned third video, and start recording the captured video frames from this starting moment of shooting. Correspondingly, if the above-mentioned face information is not detected in a certain video frame captured by the imaging device, it can be considered that the visitor leaves starting from the shooting moment of this video frame. Therefore, the imaging device may use the moment when the above-mentioned face information is not detected in this video frame as the ending moment of shooting the third video, and stop recording the captured video frames at this ending moment of shooting. In this case, the video formed by the video frames captured by the imaging device during the period from this starting moment of shooting to this ending moment of shooting is the third video.

[0069] For example, assume that the moment when the above-mentioned imaging device receives the above-mentioned third message is 16:35 on February 20, 2025, and the moment when the above-mentioned face information is not detected in the video frames captured by the imaging device itself is 16:55 on February 20, 2025. Then, the video captured by the imaging device during the period from 16:35 on February 20, 2025 to 16:55 on February 20, 2025 is the above-mentioned third video.

[0070] When the above-mentioned imaging device obtains the above-mentioned third video, it can determine that the face information detected by the imaging device during the shooting process of the third video corresponds to the third video. Therefore, the imaging device may send the corresponding relationship between the face information and the third video to the above-mentioned video recording device. Specifically, the imaging device may bind the face information to the third video, and send the bound face information and the third video to the video recording device together. When the video recording device receives the corresponding relationship between the face information and the third video, it may store this corresponding relationship, that is, it can obtain the face information and the third video, and store the face information and the third video in a corresponding manner.

[0071] It should be noted that in order to ensure the unity of face information, the above-mentioned third message may include the above-mentioned face information. In this case, on the one hand, the imaging device may match the face information detected in the video frames captured by itself with this face information, and when the two do not match, determine that the above-mentioned face information is not detected in the video frames captured by itself; on the other hand, the imaging device may directly determine that the face information in the third message corresponds to the third video.

[0072] In practical applications, as described above, the face information can be a feature vector extracted from a face image. In this case, for the above-mentioned target face information and the face information of a certain user who can unlock the lock, if the vector similarity between the feature vector as the target face information and the feature vector as the face information of the user who can unlock the lock is not less than a preset threshold, it can be considered that the target face information matches the face information of the user who can unlock the lock.

[0073] In some embodiments, the above-mentioned imaging device can be used for real-time video shooting and send the captured video to the above-mentioned video recording device for storage. That is to say, the video recording device can be used to store the video captured in real time by the imaging device.

[0074] In the above case, the above-mentioned imaging device can specifically perform face detection on the video frames captured by itself, and based on the face detection result, determine the start time and end time of shooting of the above-mentioned third video. Furthermore, the correspondence between the above-mentioned face information and the start time and end time of shooting of the third video can be sent to the above-mentioned video recording device for storage. In this way, the video recording device can extract the third video from the video captured in real time by the imaging device stored by itself according to the start time and end time of shooting of the third video.

[0075] In some embodiments, there can be multiple imaging devices deployed in the room corresponding to the above-mentioned intelligent door lock; the shooting ranges of these multiple imaging devices are usually different. For example, the shooting range of one imaging device may be the area of the room's entrance door, and the shooting range of another imaging device may be the area of the living room sofa in the room, and so on. Therefore, the start times of the video frames actually captured by each imaging device and containing human figures may be different.

[0076] Based on the above content, when each of the above-mentioned imaging devices receives the above-mentioned third message containing the above-mentioned face information, it can perform face detection on the video frames captured by itself in response to the third message. In this case, the imaging device that first detects the face information from the video frames captured by it among these imaging devices can be called the target imaging device. At this time, the target imaging device has detected the face information from the video frame, but has not yet obtained the portrait auxiliary information corresponding to the face information. Therefore, the target imaging device can obtain the portrait auxiliary information in the video frame where the face information is detected; for example, the target imaging device can perform structured analysis on the portrait area in the video frame to obtain portrait auxiliary information as the portrait auxiliary information corresponding to the target face information. Among them, the portrait auxiliary information can include the color of the clothes worn by the person, the shape of the ornaments worn by the person, and so on.

[0077] The above-mentioned target camera device can obtain a third video captured by the target camera device based on the face detection result of the video frame captured thereby. Wherein, the start time of shooting the third video captured by the target camera device can be the time when the target camera device detects the above-mentioned face information from the video frame captured thereby, and the end time of shooting the third video captured by the target camera device can be the time when the target camera device fails to detect the face information from the video frame captured thereby. That is to say, the first video captured by the target camera device can be the video captured by the target camera device during the process from when the user corresponding to the face information enters the shooting range of the target camera device to when the user leaves the shooting range of the target camera device.

[0078] After obtaining the above-mentioned portrait auxiliary information, the above-mentioned target camera device can also send the portrait auxiliary information to other camera devices in the above-mentioned camera device.

[0079] Taking any one of the above-mentioned other camera devices as an example, in response to the received portrait auxiliary information, the camera device can perform portrait auxiliary detection on the video frames captured thereby while continuing to perform face detection on the video frames captured thereby, so that the camera device can obtain a third video captured by the camera device based on the face detection result and the portrait auxiliary detection result. In practical applications, as long as the camera device detects any one of the face information and the portrait auxiliary information from the video frames captured thereby, it can be considered that the user corresponding to the face information enters the shooting range of the camera device; and when the camera device neither detects the face information nor the portrait auxiliary information from the video frames captured thereby, it can be considered that the user leaves the shooting range of the camera device. Therefore, the start time of shooting the third video captured by the camera device can be the time when the camera device detects the face information or the portrait auxiliary information from the video frames captured thereby, and the end time of shooting the third video captured by the camera device can be the time when the camera device fails to detect the face information and the portrait auxiliary information from the video frames captured thereby.

[0080] Whether it is the above-mentioned target camera device or the above-mentioned other camera devices, these camera devices can send the corresponding relationship between the above-mentioned face information and the third video captured by themselves to the above-mentioned video recording device, and the video recording device stores the corresponding relationship.

[0081] In some embodiments, the above-mentioned video recording device can obtain a video playback request. For example, a user can initiate a video playback request corresponding to a certain user through the user interface provided by the above-mentioned door lock management platform, and the door lock management platform can convert the video playback request into a video playback request corresponding to the face information according to the stored face information of the user.

[0082] In practical applications, the above-mentioned door lock management platform can serve as a backend system to manage and monitor the functions and services of a front-end application (APP) for users. Among them, the APP usually runs on a smart phone, a tablet computer or other mobile devices. It provides a user interface and interactive functions, enabling users to perform various operations. The APP can collect and generate user data and synchronize the data with the door lock management platform through an API interface. The door lock management platform can receive data from the APP, store the data in a database for subsequent analysis and processing. At the same time, the door lock management platform can also push update information, notifications or configuration changes to the APP.

[0083] When the above-mentioned video recording device obtains the above-mentioned video playback request, it can determine the first video, the second video and the third video corresponding to the face information in the video playback request according to the corresponding relationship between the stored face information and the video, and play the first video and the second video simultaneously. After the first video and the second video are played, the third video can be played continuously.

[0084] In practical applications, when the above-mentioned video recording device plays the above-mentioned first video and the above-mentioned second video simultaneously, it can specifically divide the display screen of the video recording device into two areas and play the first video and the second video respectively and simultaneously in these two areas.

[0085] When there are multiple third videos, the video frames with the same shooting time can be played simultaneously according to the shooting time of the video frames in each third video. For example, assume that the shooting time of the video frames in the first third video is from 16:35 on February 20, 2025 to 16:55 on February 20, 2025, and the shooting time of the video frames in the second third video is from 16:45 on February 20, 2025 to 17:10 on February 20, 2025. Then the video frames with the same shooting time in these two third videos are the video frames with the shooting time in the period from 16:45 on February 20, 2025 to 16:55 on February 20, 2025. Therefore, the above-mentioned video recording device can divide its own display screen into two areas, play the first third video in one area first, and then play the second third video in the other area after the first third video has been played for 10 minutes.

[0086] In the above technical solution, the intelligent door lock can call the equipped camera to take a video, and perform face detection on the captured video frames. Based on the face detection result, a first video captured by the intelligent door lock is obtained. The starting moment of shooting the first video is the moment when the intelligent door lock detects face information from the video frames captured by itself, and the ending moment of shooting the first video is the moment when the intelligent door lock detects that it has been unlocked. Furthermore, the corresponding relationship between the face information and the first video can be sent to the video recording device deployed in the room corresponding to the intelligent door lock for storage. When the intelligent door lock detects that it has been unlocked, it can also send a third message to the camera device deployed in the room, so that in response to the received third message, the camera device performs face detection on the captured video frames, and based on the face detection result, obtains a third video captured by the camera device. The starting moment of shooting the third video is the moment when the camera device receives the third message, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames captured by itself. Furthermore, the corresponding relationship between the face information and the third video can be sent to the video recording device for storage.

[0087] By adopting the above method, through the linkage among the intelligent door lock, the camera device and the video recording device deployed in the room corresponding to the intelligent door lock, the whole process of the visitor's visit can be recorded.

[0088] Based on Figure 1 , referring to Figure 3 , Figure 3 is a schematic diagram of another intelligent door lock management system shown in an exemplary embodiment of the present application.

[0089] As Figure 3 shown, in order to distinguish devices (or systems, collectively referred to as devices in this application) such as intelligent door locks, camera devices, and video recording devices in different regions, avoid unnecessary data transmission between devices in different regions, and facilitate the management of these devices in the same region, multicast can be used. The access control system and intelligent door locks in the same region can join the same multicast group. Further, the multicast data management and forwarding between the above-mentioned door lock management platform and each multicast group can be performed by a routing device supporting the multicast function (for example: router, layer 3 switch, etc.). This routing device can be directly connected to the door lock management platform and each device in the multicast group respectively.

[0090] In practical applications, in order to reduce the deployment cost of the door lock management platform, the door lock management platform can be directly deployed on the above-mentioned routing device. That is, this routing device can not only provide the multicast function, but also realize the unified management of intelligent door locks through the deployed door lock management platform.

[0091] Taking one of the multicast groups as an example, a suitable IP address can be assigned to this multicast group as the communication address of this multicast group, so that the above-mentioned door lock management platform can use this communication address to send multicast data to this multicast group. In practical applications, each device in this multicast group can also use this communication address to send multicast data to other devices in this multicast group. Each intelligent door lock, each camera device or each video recording device that needs to join this multicast group can indicate that the device hopes to join this multicast group by sending an IGMP (Internet Group Management Protocol) join message to the routing device corresponding to this multicast group. This IGMP join message can include the device information of this device (for example: device unique identifier, device geographical location, device type, etc.); after receiving this IGMP join message, the routing device can record the corresponding relationship between the device information of this device and the interface in the multicast forwarding table maintained inside it that is used to forward multicast data to this device (usually the interface used to receive this IGMP join message). And when this device no longer needs to receive multicast data, it can send an IGMP leave message to this routing device, so that this routing device stops forwarding multicast data to this device.

[0092] The corresponding relationship between the device information of each device in the above-mentioned multicast group maintained by the above-mentioned routing device and the interface can be shown in Table 3 below: Table 3

[0093] It should be noted that although Figure 3 it is shown that there is only one routing device between the above-mentioned door lock management platform and the multicast group joined by the above-mentioned intelligent door lock, in fact, in a multicast network, there can be multiple routing devices participating in the forwarding of multicast data. These routing devices all support and participate in the multicast routing protocol (such as Protocol Independent Multicast, that is, PIM).

[0094] Specifically, a multicast network can be divided into multiple subnets. For example, assume that the smart door locks corresponding to all rooms in a community (e.g., the smart door locks deployed on the entrance doors of the rooms) join the same multicast group, forming a multicast network. Then, in this multicast network, subnet division can be performed according to the building, that is, the network formed by the smart door locks corresponding to the rooms in the same building is taken as a subnet. In a subnet, there is at least one local multicast routing device responsible for receiving multicast data from the upstream and forwarding the multicast data to all multicast members in the subnet. It should be noted that if there is only one local multicast routing device in a subnet, this routing device is directly connected to the devices that are multicast members in the subnet. The upstream multicast routing device refers to the multicast routing device that is closer to the multicast source or Rendezvous Point (RP) relative to the local multicast routing device; they are responsible for receiving multicast data from the multicast source or RP and forwarding the multicast data to the downstream multicast routing devices according to the multicast routing protocol.

[0095] In a multicast network, the flow of multicast data generally includes: the multicast source sending data to the multicast routing device, the multicast routing devices forwarding data to each other, reaching the target multicast routing device, and the target multicast routing device sending data to the multicast members. Specifically, the multicast data is first sent by the multicast source to the multicast routing device directly connected to the multicast source; then, through the multicast routing protocol, these multicast data are forwarded to other multicast routing devices that need to receive this multicast stream. In this process, a multicast distribution tree is formed, which can be a source-based (*, G) or specific-source (S, G) tree, where S represents the multicast source and G represents the communication address of the multicast group; then, the multicast data will be forwarded to the target multicast routing device located at the edge of the target subnet; finally, the target multicast routing device forwards the received multicast data to the multicast members in the target subnet.

[0096] When constructing the source-based (*, G) multicast tree, this process allows multicast data from any source to be sent to the multicast address represented by G and dynamically establishes and maintains the multicast distribution path through the PIM protocol. This means that any routing device can indicate that it wishes to join this multicast group by sending a PIM join message, so as to ensure that the member devices in the subnet where the routing device is located can receive the corresponding multicast data. After receiving the PIM join message, the upstream multicast routing device will update its multicast forwarding table accordingly to ensure that the multicast data can be forwarded along the correct path.

[0097] Based on Figure 3 and referring to Figure 4 , Figure 4 is a flowchart of another video recording method based on a smart door lock shown in an exemplary embodiment of the present application.

[0098] As Figure 4 shown, the above video recording method based on an intelligent door lock can be applied to an intelligent door lock as Figure 3 shown. The method may specifically include the following steps: Step 401: Invoke the mounted camera to perform video shooting, and perform face detection on the captured video frames.

[0099] Step 402: When the face information is detected from the video frames, send a first IGMP join message to the routing device according to the communication address of the multicast group. The first IGMP join message includes the face information. When the routing device determines that the first IGMP join message also includes indication information for indicating that the intelligent door lock has detected face information, determine the neighbor intelligent door lock corresponding to the intelligent door lock according to the topological relationship, and send the first IGMP join message to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock, so that the neighbor intelligent door lock, in response to receiving the first IGMP join message, invokes the mounted camera to perform video shooting.

[0100] Step 403: When it is detected that the intelligent door lock has been unlocked, obtain the first video captured by the intelligent door lock, and send the correspondence between the face information and the first video to the video recording device deployed in the room corresponding to the intelligent door lock for storage; wherein, the start time of shooting the first video is the time when the intelligent door lock detects the face information from the video frames, and the end time of shooting the first video is the time when the intelligent door lock detects that the intelligent door lock has been unlocked.

[0101] Step 404: When it is detected that the intelligent door lock has been unlocked, send a second IGMP join message to the routing device according to the communication address of the multicast group. The second IGMP join message includes the face information. When the routing device determines that the second IGMP join message also includes indication information for indicating that the intelligent door lock has been unlocked, send the second IGMP join message to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock, so that the neighbor intelligent door lock, in response to receiving the second IGMP join message, obtains the second video captured by the neighbor intelligent door lock, and sends the correspondence between the face information and the second video to the video recording device for storage; wherein, the start time of shooting the second video is the time when the neighbor intelligent door lock receives the first message, and the end time of shooting the second video is the time when the neighbor intelligent door lock receives the second message.

[0102] Step 405: When it is detected that the intelligent door lock has been unlocked, send a second IGMP join message to the routing device according to the communication address of the multicast group. The second IGMP join message includes the face information. When the routing device determines that the second IGMP join message also includes indication information for indicating that the intelligent door lock has been unlocked, send the second IGMP join message to the camera device through the interface corresponding to the camera device deployed in the room, so that the camera device, in response to the received second IGMP join message, performs face detection on the captured video frames, obtains a third video captured by the camera device based on the face detection result, and sends the correspondence between the face information and the third video to the video recording device for storage; wherein, the start time of shooting of the third video is the time when the camera device detects the face information from the video frames, and the end time of shooting of the third video is the time when the camera device does not detect the face information from the video frames.

[0103] In this embodiment, the above intelligent door lock, the above camera device, and the above video recording device can join the same multicast group; the routing device corresponding to the multicast group can maintain the correspondence between the device information of each device in the multicast group and the interface for forwarding multicast data to the device.

[0104] In addition, the above routing device can also maintain the topological relationship between intelligent door locks, so as to facilitate determining the neighbor intelligent door locks of each intelligent door lock and the path intelligent door locks of each intelligent door lock. Specifically, this topological information can be sent by the above door lock management platform to the routing device, or can be collected by the routing device itself when receiving the above registration messages sent by each intelligent door lock to the door lock management platform through the routing device. Among them, the shooting ranges of the cameras mounted on an intelligent door lock and its neighbor intelligent door locks can be relative. The shooting ranges of the cameras mounted on an intelligent door lock and its path intelligent door locks can correspond to the user's travel route. For example, the path intelligent door locks of the intelligent door lock in Room 501, Unit 2, Building 1 can include the intelligent door locks in Room 401, Unit 2, Building 1, the intelligent door locks in Room 301, Unit 2, Building 1, the intelligent door locks in Room 201, Unit 2, Building 1, and the intelligent door locks in Room 101, Unit 2, Building 1.

[0105] When the above intelligent door lock detects face information from the video frames it captures, it can send an IGMP join message (which can be called the first IGMP join message) to the above routing device corresponding to the multicast group according to the communication address of the multicast group. Among them, the first IGMP join message can include the face information and indication information for indicating that the intelligent door lock has detected face information. At this time, the first IGMP join message can be used as the above first message.

[0106] When the above routing device receives the above first IGMP join message, if it determines that the first IGMP join message contains indication information for indicating that the above intelligent door lock has detected face information, it can determine the neighbor intelligent door lock corresponding to the intelligent door lock according to the maintained topological relationship of the intelligent door lock, and determine the interface corresponding to the neighbor intelligent door lock according to the device information of the neighbor intelligent door lock, so that the first IGMP join message can be sent to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock. When the neighbor intelligent door lock receives the first IGMP join message, it can call the mounted camera to take a video.

[0107] When the above intelligent door lock detects that it has been unlocked, it can send an IGMP join message (which can be called the second IGMP join message) to the above routing device according to the communication address of the above multicast group. Among them, the second IGMP join message can contain the above face information and indication information for indicating that the intelligent door lock has been unlocked. At this time, the second IGMP join message can be used as both the above second message and the above third message.

[0108] When the above routing device receives the above second IGMP join message, if it determines that the second IGMP join message contains indication information for indicating that the above intelligent door lock has been unlocked, on the one hand, it can send the second IGMP join message to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock, so that the neighbor intelligent door lock can obtain the above second video captured by the neighbor intelligent door lock in response to the received second IGMP join message, and send the corresponding relationship between the face information and the second video to the above video recording device for storage; on the other hand, the routing device can determine the interface corresponding to the camera device deployed in the room (specifically, the room corresponding to the intelligent door lock) according to the maintained corresponding relationship between the device information and the interface, and send the second IGMP join message to the camera device through the interface corresponding to the camera device, so that the camera device can perform face detection on the captured video frames, obtain the third video captured by the camera device based on the face detection result, and send the corresponding relationship between the face information and the third video to the above video recording device for storage.

[0109] It should be noted that there may be one and only one or multiple of the above camera devices. The above routing device can determine the interfaces corresponding to all the camera devices deployed in the room according to the maintained corresponding relationship between the device information and the interface, and send the above second IGMP join message to each camera device through these interfaces respectively.

[0110] In some embodiments, when the above-mentioned intelligent door lock detects that it is unlocked from the inside, it usually means that the user needs to leave the room. In this case, the intelligent door lock can send an IGMP join message (which can be referred to as the third IGMP join message) to the above-mentioned routing device according to the communication address of the above-mentioned multicast group. The third IGMP join message may include the above-mentioned face information and indication information for indicating that the intelligent door lock is unlocked from the inside.

[0111] When the above-mentioned routing device receives the above-mentioned third IGMP join message, if it determines that the third IGMP join message contains indication information for indicating that the above-mentioned intelligent door lock is unlocked from the inside, it can determine the path intelligent door lock corresponding to the intelligent door lock according to the topological relationship of the intelligent door lock maintained, and determine the interface corresponding to the path intelligent door lock according to the device information of the path intelligent door lock. Thus, the third IGMP join message can be sent to the path intelligent door lock through the interface corresponding to the path intelligent door lock. When the path intelligent door lock receives the third IGMP join message, it can store the face information.

[0112] It should be noted that there are usually multiple above-mentioned path intelligent door locks. The above-mentioned routing device can determine the interfaces corresponding to all path intelligent door locks according to the corresponding relationship between the device information and the interfaces maintained, and send the above-mentioned third IGMP join message to each path intelligent door lock through these interfaces respectively.

[0113] When the above-mentioned routing device determines that the third IGMP join message contains indication information for indicating that the above-mentioned intelligent door lock is unlocked from the inside, it can also determine the arrangement order of the above-mentioned path intelligent door locks according to the above-mentioned topological relationship. The arrangement order of the path intelligent door locks corresponds to the user's travel route; for example, after the user leaves the room of Room 501, Unit 2, Building 1, the arrangement order of the path intelligent door locks corresponding to the intelligent door lock of Room 501, Unit 2, Building 1 can be: the intelligent door lock of Room 401, Unit 2, Building 1 → the intelligent door lock of Room 301, Unit 2, Building 1 → the intelligent door lock of Room 201, Unit 2, Building 1 → the intelligent door lock of Room 101, Unit 2, Building 1.

[0114] The above routing device can further send the reminder message containing the above arrangement order to the first-path intelligent door lock through the interface corresponding to the first-path intelligent door lock (for example, the intelligent door lock in Room 401, Unit 2, Building 1), so that the first-path intelligent door lock can, in response to the received reminder message, call the equipped camera to take a video and perform face detection on the captured video frames. On the one hand, the first-path intelligent door lock can, based on the face detection result, obtain the video captured by the first-path intelligent door lock (which can be called the fourth video), and send the corresponding relationship between the above face information and the fourth video to the above video recording device for storage; on the other hand, when the first-path intelligent door lock fails to detect the face information from the captured video frames, it can determine the second-path intelligent door lock (i.e., the next-path intelligent door lock corresponding to the first-path intelligent door lock, for example, the intelligent door lock in Room 301, Unit 2, Building 1) according to the arrangement order in the reminder message, so that it can send the reminder message containing the arrangement order to the second-path intelligent door lock. Among them, the starting moment of the fourth video captured by the first-path intelligent door lock can be the moment when the first-path intelligent door lock detects the face information from the captured video frames, and the ending moment of the fourth video captured by the first-path intelligent door lock can be the moment when the first-path intelligent door lock fails to detect the face information from the captured video frames; that is to say, the fourth video captured by the first-path intelligent door lock can be the video captured by the first-path intelligent door lock by calling the equipped camera during the process from when the user corresponding to the face information enters the shooting range of the camera equipped on the first-path intelligent door lock to when the user leaves the shooting range of the camera equipped on the first-path intelligent door lock.

[0115] Similarly to the above-mentioned first-path intelligent door lock, the above-mentioned second-path intelligent door lock can, in response to the received reminder message containing the above arrangement order, call the mounted camera to take a video, and perform face detection on the captured video frames. On the one hand, the second-path intelligent door lock can, based on the face detection result, obtain the fourth video captured by the second-path intelligent door lock, and send the corresponding relationship between the above face information and the fourth video to the above video recording device for storage; on the other hand, when the second-path intelligent door lock fails to detect the face information from the video frames it captured, it can determine the third-path intelligent door lock (i.e., the next-path intelligent door lock corresponding to the second-path intelligent door lock, for example: the intelligent door lock of Room 201, Unit 2, Building 1) according to the arrangement order in the reminder message, so as to send the reminder message containing the arrangement order to the third-path intelligent door lock. Among them, the start time of shooting the fourth video captured by the second-path intelligent door lock can be the moment when the second-path intelligent door lock detects the face information from the video frames it captured, and the end time of shooting the fourth video captured by the second-path intelligent door lock can be the moment when the second-path intelligent door lock fails to detect the face information from the video frames it captured; that is to say, the fourth video captured by the second-path intelligent door lock can be the video captured by the second-path intelligent door lock by calling the mounted camera during the process from when the user corresponding to the face information enters the shooting range of the camera mounted on the second-path intelligent door lock to when the user leaves the shooting range of the camera mounted on the second-path intelligent door lock.

[0116] And so on, until all the path intelligent door locks corresponding to the above intelligent door lock have completed the shooting of the fourth video, and sent the corresponding relationship between the above face information and the fourth video captured by each of them to the above video recording device for storage.

[0117] It should be noted that when each path intelligent door lock sends the corresponding relationship between the above face information and the fourth video captured by it to the above video recording device for storage, specifically, the path intelligent door lock can bind the face information and the fourth video captured by it, and send the bound face information and fourth video to the video recording device together. The video recording device can receive the bound face information and fourth video, that is, receive the corresponding relationship between the face information and the fourth video, so that the video recording device can store the corresponding relationship, that is, the video recording device can obtain the face information and the fourth video, and store the face information and the fourth video corresponding to each other.

[0118] In some embodiments, in order to reduce the power consumption of the above-mentioned intelligent door lock and extend the operable duration of the intelligent door lock under the same amount of power, each path intelligent door lock can switch from the sleep state to the running state when receiving the above-mentioned reminder message, so as to call the mounted camera to perform video shooting.

[0119] It should be noted that when the above-mentioned door lock management platform, any intelligent door lock, any camera device or any video recording device needs to send specific data to any one or more devices (which can be called target devices) in the above-mentioned multicast group, it can send the data and the device information of the target device (for example: the floor where it is located, the corresponding room, the device type, the identification information, etc.) to the routing device corresponding to the multicast group according to the communication address of the multicast group. The routing device determines the interface corresponding to the target device according to the device information, and sends the data to the target device through this interface.

[0120] Such as Figure 4 shown, the specific implementation manner of the embodiment can refer to the embodiment shown in Figure 2 shown, and details are not described herein again in this application.

[0121] Corresponding to the embodiment of the foregoing method, the present application also provides an embodiment of a device.

[0122] Refer to Figure 5 , Figure 5 which is a schematic structural diagram of a device shown in an exemplary embodiment of the present application. At the hardware level, the device includes a processor 501, an internal bus 502, a network interface 503, a memory 504, and a non-volatile memory 505. Of course, other required hardware may also be included. One or more embodiments of the present application can be implemented in a software manner. For example, the processor 501 reads the corresponding computer program from the non-volatile memory 505 into the memory 504 and then runs it. Of course, in addition to the software implementation manner, one or more embodiments of the present application do not exclude other implementation manners, such as a logic device or a combination of software and hardware. That is to say, the execution subject of the following processing flow is not limited to each logic module, and can also be hardware or a logic device.

[0123] Refer to Figure 6 , Figure 6 which is a block diagram of a video recording device based on an intelligent door lock shown in an exemplary embodiment of the present application.

[0124] The above-mentioned video recording device based on an intelligent door lock can be applied to Figure 5 the device shown, and the device can be an intelligent door lock to implement the technical solution of the present application.

[0125] Such as Figure 6 shown, the above-mentioned video recording device based on an intelligent door lock may specifically include: The detection module 601 is configured to call the mounted camera to perform video shooting and perform face detection on the captured video frames; The first video recording module 602 is configured to, when face information is detected from the video frames, send a first message including the face information to a neighbor smart door lock corresponding to the smart door lock, so that the neighbor smart door lock, in response to the received first message, calls the mounted camera to perform video shooting; The second video recording module 603 is configured to, when it is detected that the smart door lock has been unlocked, obtain a first video captured by the smart door lock, and send the correspondence between the face information and the first video to a video recording device deployed in the room corresponding to the smart door lock for storage; and send a second message to the neighbor smart door lock, so that the neighbor smart door lock, in response to the received first message, obtains a second video captured by the neighbor smart door lock, and sends the correspondence between the face information and the second video to the video recording device for storage; and send a third message including the face information to a camera device deployed in the room, so that the camera device, in response to the received third message, performs face detection on the captured video frames, and based on the face detection result, obtains a third video captured by the camera device, and sends the correspondence between the face information and the third video to the video recording device for storage; Wherein, the starting moment of shooting the first video is the moment when the smart door lock detects the face information from the video frames, and the ending moment of shooting the first video is the moment when the smart door lock detects that the smart door lock has been unlocked; the starting moment of shooting the second video is the moment when the neighbor smart door lock receives the first message, and the ending moment of shooting the second video is the moment when the neighbor smart door lock receives the second message; the starting moment of shooting the third video is the moment when the camera device detects the face information from the video frames, and the ending moment of shooting the third video is the moment when the camera device does not detect the face information from the video frames.

[0126] In some embodiments, the video recording device is configured to, when a video playback request is obtained, determine the first video, the second video, and the third video stored corresponding to the face information in the video playback request, and play the first video and the second video simultaneously, and after the playback is completed, continue to play the third video.

[0127] In some embodiments, the calling the mounted camera to perform video shooting includes: Calling the mounted camera to perform real-time video shooting; or, When it is detected that a user enters the detection range of the intelligent door lock, the mounted camera is called to take a video.

[0128] In some embodiments, when it is detected that a user enters the detection range of the intelligent door lock, calling the mounted camera to take a video includes: When it is detected that a user enters the detection range of the intelligent door lock, switching from the sleep state to the running state to call the mounted camera to take a video.

[0129] In some embodiments, the camera device is used to take a real-time video and send the captured video to the video recording device for storage; Sending a third message containing the face information to the camera device deployed in the room corresponding to the intelligent door lock, so that in response to the received third message, the camera device performs face detection on the captured video frames, based on the face detection result, obtains a third video captured by the camera device, and sends the correspondence between the face information and the third video to the video recording device for storage, includes: Sending a third message containing the face information to the camera device deployed in the room corresponding to the intelligent door lock, so that in response to the received third message, the camera device performs face detection on the captured video frames, based on the face detection result, determines the start time and end time of shooting of the third video captured by the camera device, and sends the correspondence between the face information and the start time and end time of shooting of the third video to the video recording device for storage.

[0130] In some embodiments, sending a third message containing the face information to the camera device deployed in the room, so that in response to the received third message, the camera device performs face detection on the captured video frames, based on the face detection result, obtains a third video captured by the camera device, and sends the correspondence between the face information and the third video to the video recording device for storage, includes: Send a third message containing the face information to the camera device deployed in the room, so that in response to the received third message, the camera device performs face detection on the captured video frames. When the target camera device in the camera device detects the face information from the video frames and has not obtained the portrait auxiliary information corresponding to the face information, the target camera device obtains the portrait auxiliary information in the video frames, and sends the portrait auxiliary information to other camera devices in the camera device. And based on the face detection result, obtain the third video captured by the target camera device, and send the correspondence between the face information and the third video to the video recording device for storage. The other camera devices perform portrait auxiliary detection on the captured video frames in response to the received portrait auxiliary information, and based on the face detection result and the portrait auxiliary detection result, obtain the third video captured by the other camera devices, and send the correspondence between the face information and the third video to the video recording device for storage; Among them, the start time of shooting the third video captured by the target camera device is the time when the target camera device detects the face information from the video frames, and the end time of shooting the third video is the time when the target camera device does not detect the face information from the video frames; the start time of shooting the third video captured by the other camera devices is the time when the other camera devices detect the face information or the portrait auxiliary information from the video frames, and the end time of shooting the third video is the time when the other camera devices do not detect the face information and the portrait auxiliary information from the video frames.

[0131] In some embodiments, the intelligent door lock, the camera device and the video recording device join the same multicast group; the routing device corresponding to the multicast group maintains the correspondence between the identification information of the device and the interface; the routing device also maintains the topological relationship between the intelligent door locks; When detecting the face information from the video frames, send a first message containing the face information to the neighbor intelligent door lock corresponding to the intelligent door lock, so that in response to the received first message, the neighbor intelligent door lock calls the mounted camera for video shooting, including: When the face information is detected from the video frame, a first IGMP join message including the face information is sent to the routing device according to the communication address of the multicast group. When the routing device determines that the first IGMP join message further includes indication information for indicating that the intelligent door lock has detected face information, the neighbor intelligent door lock corresponding to the intelligent door lock is determined according to the topological relationship, and the first IGMP join message is sent to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock, so that the neighbor intelligent door lock responds to the received first IGMP join message and calls the mounted camera to perform video shooting; When it is detected that the intelligent door lock has been unlocked, a second message is sent to the neighbor intelligent door lock, so that the neighbor intelligent door lock responds to the received first message, obtains a second video captured by the neighbor intelligent door lock, and sends the correspondence between the face information and the second video to the video recording device for storage; and, a third message including the face information is sent to the camera device deployed in the room, so that the camera device responds to the received third message, performs face detection on the captured video frame, obtains a third video captured by the camera device based on the face detection result, and sends the correspondence between the face information and the third video to the video recording device for storage, including: When it is detected that the intelligent door lock has been unlocked, a second IGMP join message including the face information is sent to the routing device according to the communication address of the multicast group. When the routing device determines that the second IGMP join message further includes indication information for indicating that the intelligent door lock has been unlocked, the second IGMP join message is sent to the neighbor intelligent door lock through the interface corresponding to the neighbor intelligent door lock, so that the neighbor intelligent door lock responds to the received second IGMP join message, obtains a second video captured by the neighbor intelligent door lock, and sends the correspondence between the face information and the second video to the video recording device for storage; and, when the routing device determines that the second IGMP join message further includes indication information for indicating that the intelligent door lock has been unlocked, the second IGMP join message is sent to the camera device through the interface corresponding to the camera device deployed in the room, so that the camera device responds to the received second IGMP join message, performs face detection on the captured video frame, obtains a third video captured by the camera device based on the face detection result, and sends the correspondence between the face information and the third video to the video recording device for storage.

[0132] In some embodiments, the device further includes: A third video module, configured to, when detecting that the intelligent door lock is unlocked from the inside, send a third IGMP join message to the routing device according to the communication address of the multicast group, where the third IGMP join message includes the face information. When the routing device determines that the third IGMP join message further includes indication information for indicating that the intelligent door lock is unlocked from the inside, the routing device determines a path intelligent door lock corresponding to the intelligent door lock according to the topological relationship, and sends the third IGMP message to the path intelligent door lock through an interface corresponding to the path intelligent door lock, so that the path intelligent door lock stores the face information. And when the routing device determines that the third IGMP join message further includes indication information for indicating that the intelligent door lock is unlocked from the inside, the routing device determines the arrangement order of the path intelligent door locks corresponding to the intelligent door lock according to the topological relationship, and sends a reminder message including the arrangement order to the first path intelligent door lock through an interface corresponding to the first path intelligent door lock, so that the first path intelligent door lock, in response to the received reminder message, calls the mounted camera to perform video shooting, performs face detection on the captured video frames, obtains a fourth video captured by the first path intelligent door lock based on the face detection result, and sends the correspondence between the face information and the fourth video to the video recording device for storage. When the face information is not detected from the video frames, the reminder message is sent to the next intelligent door lock corresponding to the first path intelligent door lock; Wherein, the starting moment of shooting the fourth video is the moment when the first path intelligent door lock detects the face information from the video frames, and the ending moment of shooting the fourth video is the moment when the first path intelligent door lock does not detect the face information from the video frames.

[0133] In some embodiments, when receiving the reminder message, the path intelligent door lock switches from the sleep state to the running state to call the mounted camera to perform video shooting.

[0134] In some embodiments, the correspondence between the device information and the interface is created by the routing device according to the device information of each device included in the IGMP join message sent by each device in the multicast group and the interface in the routing device for receiving the IGMP join message.

[0135] Corresponding to the embodiments of the foregoing method, the present application further provides an embodiment of a system.

[0136] A video recording system based on an intelligent door lock, the system includes an intelligent door lock, a neighbor intelligent door lock corresponding to the intelligent door lock, a camera device and a video recording device deployed in a room corresponding to the intelligent door lock; wherein: The intelligent door lock calls the built-in camera to take a video and performs face detection on the captured video frames; When the intelligent door lock detects the face information from the video frames, it sends a first message containing the face information to the neighboring intelligent door lock corresponding to the intelligent door lock; In response to receiving the first message, the neighboring intelligent door lock calls the built-in camera to take a video; When the intelligent door lock detects that the intelligent door lock has been unlocked, it obtains the first video captured by the intelligent door lock and sends the correspondence between the face information and the first video to the video recording device deployed in the room corresponding to the intelligent door lock for storage; and, sends a second message to the neighboring intelligent door lock; and, sends a third message containing the face information to the camera device deployed in the room; In response to receiving the first message, the neighboring intelligent door lock obtains the second video captured by the neighboring intelligent door lock and sends the correspondence between the face information and the second video to the video recording device for storage; In response to receiving the third message, the camera device performs face detection on the captured video frames, obtains the third video captured by the camera device based on the face detection result, and sends the correspondence between the face information and the third video to the video recording device for storage; Wherein, the start time of shooting the first video is the time when the intelligent door lock detects the face information from the video frames, and the end time of shooting the first video is the time when the intelligent door lock detects that the intelligent door lock has been unlocked; the start time of shooting the second video is the time when the neighboring intelligent door lock receives the first message, and the end time of shooting the second video is the time when the neighboring intelligent door lock receives the second message; the start time of shooting the third video is the time when the camera device detects the face information from the video frames, and the end time of shooting the third video is the time when the camera device does not detect the face information from the video frames.

[0137] In some embodiments, when the video recording device receives a video playback request, it determines the first video, the second video, and the third video stored corresponding to the face information in the video playback request, plays the first video and the second video simultaneously, and after the playback is completed, continues to play the third video.

[0138] In some embodiments, the intelligent door lock specifically performs: Calls the built-in camera to take a real-time video; or, In some embodiments, the intelligent door lock specifically performs: When it is detected that the user enters the detection range of the intelligent door lock, it switches from the sleep state to the running state to call the equipped camera for video shooting.

[0139] In some embodiments, the camera device is used for real-time video shooting and sends the captured video to the video recording device for storage; The camera device specifically executes: Send a third message containing the face information to the camera device deployed in the room corresponding to the intelligent door lock, so that the camera device, in response to the received third message, performs face detection on the captured video frames, and based on the face detection result, determines the shooting start time and shooting end time of the third video captured by the camera device, and sends the correspondence between the face information and the shooting start time and shooting end time of the third video to the video recording device for storage.

[0140] In some embodiments, the camera device specifically executes: In response to the received third message, perform face detection on the captured video frames. When the target camera device in the camera device detects the face information from the video frames and does not obtain the portrait auxiliary information corresponding to the face information, obtain the portrait auxiliary information in the video frames, and send the portrait auxiliary information to other camera devices in the camera device, and based on the face detection result, obtain the third video captured by the target camera device, and send the correspondence between the face information and the third video to the video recording device for storage. The other camera devices, in response to the received portrait auxiliary information, perform portrait auxiliary detection on the captured video frames, and based on the face detection result and the portrait auxiliary detection result, obtain the third video captured by the other camera devices, and send the correspondence between the face information and the third video to the video recording device for storage; Among them, the shooting start time of the third video captured by the target camera device is the time when the target camera device detects the face information from the video frames, and the shooting end time of the third video is the time when the target camera device does not detect the face information from the video frames; the shooting start time of the third video captured by the other camera devices is the time when the other camera devices detect the face information or the portrait auxiliary information from the video frames, and the shooting end time of the third video is the time when the other camera devices do not detect the face information and the portrait auxiliary information from the video frames.

[0141] In some embodiments, the intelligent door lock, the camera device, and the video recording device join the same multicast group; a routing device corresponding to the multicast group maintains the correspondence between the identification information of the devices and the interfaces; the routing device also maintains the topological relationship between the intelligent door locks; The intelligent door lock specifically executes: When the face information is detected from the video frame, according to the communication address of the multicast group, send a first IGMP join message to the routing device, where the first IGMP join message includes the face information; The routing device executes: When it is determined that the first IGMP join message further includes indication information for indicating that the intelligent door lock has detected face information, according to the topological relationship, determine the neighboring intelligent door locks corresponding to the intelligent door lock, and send the first IGMP join message to the neighboring intelligent door locks through the interfaces corresponding to the neighboring intelligent door locks; The neighboring intelligent door lock specifically executes: In response to receiving the first IGMP join message, call the mounted camera to perform video shooting; The intelligent door lock specifically executes: When it is detected that the intelligent door lock has been unlocked, according to the communication address of the multicast group, send a second IGMP join message to the routing device, where the second IGMP join message includes the face information; The routing device further executes: When it is determined that the second IGMP join message further includes indication information for indicating that the intelligent door lock has been unlocked, send the second IGMP join message to the neighboring intelligent door locks through the interfaces corresponding to the neighboring intelligent door locks; and send the second IGMP join message to the camera device through the interfaces corresponding to the camera devices deployed in the room.

[0142] The neighboring intelligent door lock specifically executes: In response to receiving the second IGMP join message, obtain a second video captured by the neighboring intelligent door lock, and send the correspondence between the face information and the second video to the video recording device for storage; The camera device specifically executes: In response to receiving the second IGMP join message, perform face detection on the captured video frames, based on the face detection results, obtain a third video captured by the camera device, and send the correspondence between the face information and the third video to the video recording device for storage.

[0143] In some embodiments, the intelligent door lock further executes: When it is detected that the intelligent door lock is unlocked from the inside, a third IGMP join message is sent to the routing device according to the communication address of the multicast group, and the third IGMP join message includes the face information; The routing device also performs: When it is determined that the third IGMP join message also includes indication information for indicating that the intelligent door lock is unlocked from the inside, according to the topological relationship, determine the path intelligent door lock corresponding to the intelligent door lock, and send the third IGMP message to the path intelligent door lock through the interface corresponding to the path intelligent door lock; and, determine the arrangement order of the path intelligent door locks corresponding to the intelligent door lock, and send a reminder message including the arrangement order to the first path intelligent door lock through the interface corresponding to the first path intelligent door lock; The path intelligent door lock performs: Store the face information; The first path intelligent door lock performs: In response to the received reminder message, call the mounted camera to take a video, perform face detection on the captured video frame, based on the face detection result, obtain a fourth video captured by the first path intelligent door lock, and send the correspondence between the face information and the fourth video to the video recording device for storage. When the face information is not detected from the video frame, send the reminder message to the next intelligent door lock corresponding to the first path intelligent door lock; Wherein, the start time of shooting the fourth video is the time when the first path intelligent door lock detects the face information from the video frame, and the end time of shooting the fourth video is the time when the first path intelligent door lock does not detect the face information from the video frame.

[0144] In some embodiments, when the path intelligent door lock receives the reminder message, it switches from the sleep state to the running state to call the mounted camera to take a video.

[0145] In some embodiments, the correspondence between the device information and the interface is created by the routing device according to the device information included in the IGMP join messages sent by each device in the multicast group and the interface in the routing device for receiving the IGMP join messages.

[0146] For the apparatus embodiments and system embodiments, they basically correspond to the method embodiments. Therefore, for the relevant parts, please refer to the partial descriptions of the method embodiments. The apparatus embodiments and system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the technical solution of this application.

[0147] The systems, apparatuses, modules or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver device, a game console, a tablet computer, a wearable device, or a combination of any several of these devices.

[0148] In a typical configuration, a computer includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0149] The memory may include non-permanent memory in the computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0150] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic disk storage, quantum memory, graphene-based storage media, or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0151] It should be noted that the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or device including the said element.

[0152] The above describes specific embodiments of the present application. Other embodiments are within the scope of the present application. In some cases, the actions or steps recited in the present application may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0153] The terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of the present application. The singular forms "a", "the" and "said" are also intended to include the plural forms unless the context clearly dictates otherwise. The term "and / or" refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0154] The description of the terms "an embodiment", "some embodiments", "example", "specific example" or "a mode of implementation" etc. used in one or more embodiments of the present application means that the specific features or characteristics described in connection with the embodiment are included in at least one embodiment of the present application. The schematic description of these terms does not necessarily refer to the same embodiment. Moreover, the specific features or characteristics described can be combined in a suitable manner in one or more embodiments of the present application. In addition, different embodiments and the specific features or characteristics in different embodiments can be combined without contradiction.

[0155] It should be understood that although the terms first, second, third, etc. may be used in one or more embodiments of the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0156] The above are only the preferred embodiments of one or more embodiments of the present application, and are not intended to limit one or more embodiments of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of one or more embodiments of the present application shall be included within the scope of protection of one or more embodiments of the present application.

[0157] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

Claims

1. A video recording method based on a smart door lock, applied to a smart door lock; the method comprises: Call the onboard camera to shoot video and perform face detection on the captured video frames; When face information is detected from the video frame, a first message containing the face information is sent to a neighboring smart door lock corresponding to the smart door lock, so that the neighboring smart door lock responds to the received first message and calls the mounted camera to shoot a video; When it is detected that the smart door lock is unlocked, a first video captured by the smart door lock is obtained, and the correspondence between the facial information and the first video is sent to a video recording device deployed in a room corresponding to the smart door lock for storage; and a second message is sent to the neighbor smart door lock, so that the neighbor smart door lock responds to the received first message, obtains a second video captured by the neighbor smart door lock, and sends the correspondence between the facial information and the second video to the video recording device for storage; and a third message containing the facial information is sent to a video recording device deployed in the room, so that the video recording device responds to the received third message, performs face detection on the captured video frame, obtains a third video captured by the video recording device based on the face detection result, and sends the correspondence between the facial information and the third video to the video recording device for storage; Among them, the starting time of shooting the first video is the time when the smart door lock detects the facial information from the video frame, and the ending time of shooting the first video is the time when the smart door lock detects that the smart door lock is unlocked; the starting time of shooting the second video is the time when the neighbor smart door lock receives the first message, and the ending time of shooting the second video is the time when the neighbor smart door lock receives the second message; the starting time of shooting the third video is the time when the camera device detects the facial information from the video frame, and the ending time of shooting the third video is the time when the camera device does not detect the facial information from the video frame.

2. According to the method described in claim 1, the recording device is used to determine the stored first video, second video and third video corresponding to the facial information in the video playback request when receiving the video playback request, and play the first video and the second video at the same time, and continue to play the third video after the playback is completed.

3. According to the method of claim 1, calling the carried camera to shoot the video comprises: Call the onboard camera to shoot real-time video; or, When it is detected that a user enters the detection range of the smart door lock, the onboard camera is called to shoot a video.

4. The method according to claim 1, wherein the camera device is used for real-time video capture and the captured video is sent to the video recording device for storage; The sending of a third message containing the facial information to a camera device deployed in a room corresponding to the smart door lock, so that the camera device performs face detection on the captured video frame in response to the received third message, obtains a third video captured by the camera device based on the face detection result, and sends the corresponding relationship between the facial information and the third video to the video recording device for storage, including: A third message containing the facial information is sent to a camera device deployed in a room corresponding to the smart door lock, so that the camera device performs face detection on the captured video frames in response to the received third message, determines the shooting start time and shooting end time of the third video captured by the camera device based on the face detection result, and sends the correspondence between the facial information and the shooting start time and shooting end time of the third video to the recording device for storage.

5. The method according to claim 1, wherein the sending a third message containing the facial information to the camera device deployed in the room so that the camera device performs face detection on the captured video frames in response to the received third message, obtains a third video captured by the camera device based on the face detection result, and sends the corresponding relationship between the facial information and the third video to the video recording device for storage, comprising: Sending a third message containing the facial information to the camera devices deployed in the room, so that the camera devices perform face detection on the captured video frames in response to the received third message, and when the target camera device among the camera devices detects the facial information from the video frames and fails to obtain the portrait auxiliary information corresponding to the facial information, obtains the portrait auxiliary information in the video frames, and sends the portrait auxiliary information to other camera devices among the camera devices, and based on the face detection result, obtains a third video captured by the target camera device, and sends the corresponding relationship between the facial information and the third video to the video recording device for storage, and the other camera devices perform portrait auxiliary detection on the captured video frames in response to the received portrait auxiliary information, and based on the face detection result and the portrait auxiliary detection result, obtains the third video captured by the other camera devices, and sends the corresponding relationship between the facial information and the third video to the video recording device for storage; Among them, the shooting start time of the third video captured by the target camera device is the moment when the target camera device detects the facial information from the video frame, and the shooting end time of the third video is the moment when the target camera device does not detect the facial information from the video frame; the shooting start time of the third video captured by the other camera devices is the moment when the other camera devices detect the facial information or the portrait auxiliary information from the video frame, and the shooting end time of the third video is the moment when the other camera devices do not detect the facial information and the portrait auxiliary information from the video frame.

6. According to the method of claim 1, the smart door lock, the camera device and the video recording device join the same multicast group; the routing device corresponding to the multicast group maintains the corresponding relationship between the identification information of the device and the interface; The routing device also maintains the topological relationship between the smart door locks; When face information is detected from the video frame, a first message containing the face information is sent to a neighboring smart door lock corresponding to the smart door lock, so that the neighboring smart door lock responds to the received first message and calls the carried camera to shoot the video, including: When the face information is detected from the video frame, a first IGMP join message is sent to the routing device according to the communication address of the multicast group, wherein the first IGMP join message includes the face information, and when the routing device determines that the first IGMP join message also includes indication information for indicating that the smart door lock has detected the face information, a neighbor smart door lock corresponding to the smart door lock is determined according to the topological relationship, and the first IGMP join message is sent to the neighbor smart door lock through an interface corresponding to the neighbor smart door lock, so that the neighbor smart door lock responds to the received first IGMP join message and calls the carried camera to shoot the video; When it is detected that the smart door lock is unlocked, a second message is sent to the neighbor smart door lock, so that the neighbor smart door lock responds to the received first message, obtains a second video shot by the neighbor smart door lock, and sends the corresponding relationship between the facial information and the second video to the video recording device for storage; and a third message containing the facial information is sent to the camera device deployed in the room, so that the camera device responds to the received third message, performs face detection on the captured video frame, obtains a third video shot by the camera device based on the face detection result, and sends the corresponding relationship between the facial information and the third video to the video recording device for storage, including: When it is detected that the smart door lock is unlocked, a second IGMP join message is sent to the routing device according to the communication address of the multicast group, where the second IGMP join message includes the facial information. When the routing device determines that the second IGMP join message also includes indication information for indicating that the smart door lock is unlocked, the second IGMP join message is sent to the neighboring smart door lock through an interface corresponding to the neighboring smart door lock, so that the neighboring smart door lock responds to the received second IGMP join message, obtains the second video captured by the neighboring smart door lock, and compares the facial information with the first The corresponding relationship between the two videos is sent to the recording device for storage; and, when the routing device determines that the second IGMP join message also includes indication information for indicating that the smart door lock has been unlocked, the second IGMP join message is sent to the camera device through an interface corresponding to the camera device deployed in the room, so that the camera device responds to the received second IGMP join message, performs face detection on the captured video frames, obtains the third video captured by the camera device based on the face detection result, and sends the corresponding relationship between the face information and the third video to the recording device for storage.

7. The method according to claim 6, further comprising: When it is detected that the smart door lock is unlocked from the inside, a third IGMP join message is sent to the routing device according to the communication address of the multicast group, and the third IGMP join message includes the facial information. When the routing device determines that the third IGMP join message also includes indication information for instructing the smart door lock to unlock from the inside, the path smart door lock corresponding to the smart door lock is determined according to the topological relationship, and the third IGMP message is sent to the path smart door lock through the interface corresponding to the path smart door lock, so that the path smart door lock stores the facial information; and when the routing device determines that the third IGMP join message also includes indication information for instructing the smart door lock to unlock from the inside , according to the topological relationship, determine the arrangement order of the path smart door locks corresponding to the smart door lock, and send a reminder message containing the arrangement order to the first path smart door lock through the interface corresponding to the first path smart door lock, so that the first path smart door lock responds to the received reminder message, calls the carried camera to shoot video, and performs face detection on the captured video frame, obtains the fourth video shot by the first path smart door lock based on the face detection result, and sends the corresponding relationship between the face information and the fourth video to the recording device for storage, and when the face information is not detected from the video frame, sends the reminder message to the next smart door lock corresponding to the first path smart door lock; Among them, the starting time of shooting the fourth video is the time when the first path smart door lock detects the facial information from the video frame, and the ending time of shooting the fourth video is the time when the first path smart door lock does not detect the facial information from the video frame.

8. According to the method of claim 7, when the path smart door lock receives the reminder message, it switches from the sleep state to the running state to call the onboard camera to take video shots.

9. A video recording system based on a smart door lock, the system comprising a smart door lock, a neighboring smart door lock corresponding to the smart door lock, a camera device and a video recording device deployed in a room corresponding to the smart door lock; wherein: The smart door lock uses the camera to shoot video and performs face detection on the captured video frames; When the smart door lock detects the face information from the video frame, the smart door lock sends a first message containing the face information to a neighbor smart door lock corresponding to the smart door lock; In response to the received first message, the neighbor smart door lock calls the mounted camera to shoot a video; When the smart door lock detects that the smart door lock has been unlocked, the smart door lock obtains a first video captured by the smart door lock, and sends the correspondence between the facial information and the first video to a video recording device deployed in a room corresponding to the smart door lock for storage; and sends a second message to the neighbor smart door lock; And, sending a third message including the facial information to a camera device deployed in the room; In response to the received first message, the neighbor smart door lock obtains a second video captured by the neighbor smart door lock, and sends the corresponding relationship between the facial information and the second video to the video recording device for storage; The camera device performs face detection on the captured video frame in response to the received third message, obtains a third video captured by the camera device based on the face detection result, and sends the corresponding relationship between the face information and the third video to the video recording device for storage; Among them, the starting time of shooting the first video is the time when the smart door lock detects the facial information from the video frame, and the ending time of shooting the first video is the time when the smart door lock detects that the smart door lock is unlocked; the starting time of shooting the second video is the time when the neighbor smart door lock receives the first message, and the ending time of shooting the second video is the time when the neighbor smart door lock receives the second message; the starting time of shooting the third video is the time when the camera device detects the facial information from the video frame, and the ending time of shooting the third video is the time when the camera device does not detect the facial information from the video frame.

10. According to the system of claim 9, the smart door lock, the camera device and the video recording device join the same multicast group; the routing device corresponding to the multicast group maintains the corresponding relationship between the identification information of the device and the interface; The routing device also maintains the topological relationship between the smart door locks; When the smart door lock detects the face information from the video frame, the smart door lock sends a first message containing the face information to a neighboring smart door lock corresponding to the smart door lock, including: When the smart door lock detects the face information from the video frame, the smart door lock sends a first IGMP join message to the routing device according to the communication address of the multicast group, where the first IGMP join message includes the face information; When the routing device determines that the first IGMP join message further includes indication information for indicating that the smart door lock detects face information, the routing device determines a neighbor smart door lock corresponding to the smart door lock according to the topological relationship, and sends the first IGMP join message to the neighbor smart door lock through an interface corresponding to the neighbor smart door lock; When the smart door lock detects that the smart door lock has been unlocked, the smart door lock sends a second message to the neighbor smart door lock; and sends a third message containing the face information to the camera device deployed in the room, including: When the smart door lock detects that the smart door lock has been unlocked, the smart door lock sends a second IGMP join message to the routing device according to the communication address of the multicast group, where the second IGMP join message includes the face information; When the routing device determines that the second IGMP join message also includes indication information for indicating that the smart door lock has been unlocked, the routing device sends the second IGMP join message to the neighbor smart door lock through the interface corresponding to the neighbor smart door lock; and sends the second IGMP join message to the camera device deployed in the room through the interface corresponding to the camera device.

Images